Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 1.6T | 123B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 1M | 256k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.90Relace | $0.40Mistral |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.50Relace | $2.00Mistral |
| $255Relace · fp4 | $180Mistral | |
| These models have no shared benchmark scores. | ||
CheatBenchCheating rate — Measures how often AI agents try to cheat on difficult assignments, such as reading hidden answers, copying work or manipulating grading. The overall score gives equal weight to ten categories; the sycophancy category measures how far an agent shifts its beliefs toward a user's stated views. Scores describe each model in its tested agent setup, and task success is measured separately. Lower is better. | 75.1% | — |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 14% | — |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 72.2% |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 61.3% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 93.5% | — |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 32.6% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.1% | — |
| Overview | ||
| Company | DeepSeek | Mistral |
| Release date | Apr 24 2026 | Dec 9 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-ProvsClaude Haiku 5.5Devstral 2 (123B)vsClaude Haiku 5.5DeepSeek-V4-ProvsGPT-6.1 SolDevstral 2 (123B)vsGPT-6.1 SolDeepSeek-V4-ProvsGemini 4 ArgonDevstral 2 (123B)vsGemini 4 ArgonDeepSeek-V4-ProvsMuse Spark OpenDevstral 2 (123B)vsMuse Spark OpenDeepSeek-V4-ProvsGrok 4.7Devstral 2 (123B)vsGrok 4.7DeepSeek-V4-ProvsKimi K3Devstral 2 (123B)vsKimi K3Frequently asked questions
DeepSeek-V4-Pro and Devstral 2 (123B) don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Devstral 2 (123B) shipped 136 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Pro has 1.6T parameters, while Devstral 2 (123B) has 123B. Context windows are 1M (DeepSeek-V4-Pro) vs 256k (Devstral 2 (123B)).
Direct benchmark comparisons are unavailable — DeepSeek-V4-Pro and Devstral 2 (123B) don't publish scores on any of the same benchmarks.